Progress in Vehicle Recognition Methods based on Machine Vision

Huiru Dai; Xinyu Wu; Xiaoxiao Niu; Jingyuan He

doi:10.6919/ICJE.202512_11(12).0008

Authors

Huiru Dai
Xinyu Wu
Xiaoxiao Niu
Jingyuan He

DOI:

https://doi.org/10.6919/ICJE.202512_11(12).0008

Keywords:

Machine Vision; Vehicle Recognition; Feature Analysis; Convolutional Neural Networks; Multimodal Fusion.

Abstract

With the continuous growth of car drivers, the problems and needs on the road increase, and vision-based intelligent transportation technology becomes more and more important. Vehicle recognition algorithms based on machine vision face many challenges in the field of intelligent transportation, such as complex visual scenes during driving, conventional deep learning models are greatly affected by environmental factors, and limited memory and computing power of on-board embedded devices. In order to deeply analyze the application and research status of deep learning networks in vehicle recognition, the application of various current object detection methods in vehicle recognition is first introduced, and then the practical application status of real-time detection algorithms is described in detail. Finally, the advantages and disadvantages of these algorithms are compared and analyzed.

Downloads

Download data is not yet available.

References

[1] G.E. Hinton, R.R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science. Vol. 313 (2006) No. 5786, p. 504-507.

[2] S. Ren, K. He, R. Girshick, et al. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems. Vol. 28 (2015), p. 1137-1149.

[3] J. Redmon, S. Divvala, R. Girshick, et al. You only look once: Unified, realtime object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA, 27-30 Jun. 2016. Vol. (2016) , p. 779-788.

[4] J. Redmon, A. Farhadi. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767. Vol. (2018).

[5] Wen, X. Z., Fang, W., Zheng, Y. H., et al. A vehicle recognition algorithm based on Haar-like features and improved AdaBoost classifier. Acta Electronica Sinica. Vol. 39 (2011) No. 5, p. 1121-1126.

[6] Deng, L., Wang, Z., et al. Research on vehicle type recognition based on deep convolutional neural network. Application Research of Computers. Vol. 33 (2016) No. 3, p. 930-932.

[7] Cheng, Q., Fan, Y., Liu, Y. C., et al. Vehicle recognition technology based on multi-feature fusion. Infrared and Laser Engineering. Vol. 47 (2018) No. 7, p. 316-321.

[8] Watkins R, Pears N, Manandhar S. Vehicle classification using ResNets, localisation and spatially-weighted pooling. Elsevier, 2018.

[9] Jocher, G., Liu C Y, Hogan A, et al. Ultralytics YOLOv5: State-of-the-Art Object Detection. GitHub Repository, 2020.

[10] Tan, M., & Le, Q. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. ICML 2019.

[11] Chen, X., et al. BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers. CVPR 2022.

[12] Howard, A., et al. Searching for MobileNetV3. ICCV 2019.

[13] Chen, T., et al. A Simple Framework for Contrastive Learning of Visual Representations. ICML 2020.

[14] J. Redmon, A. Farhadi. YOLO9000: Better, faster, stronger. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA, 21-26 Jul. 2017. Vol. (2017) , p. 7263-7271.

[15] Z. Ge, S. Liu F. Wang, Z. Li, et al. YOLOX: Exceeding YOLO Series in 2021. arXiv preprint arXiv:2107.08430. Vol. (2021).

[16] Gao, Y. T., Ning, H., Wang, W., et al. Research on vehicle model recognition based on convolutional neural network. Applied Science and Technology. Vol. 45 (2018) No. 6, p. 53-58+62.

[17] Guan, D. Y., Ju, M., An, L. H. Research on vehicle body color recognition technology based on convolutional neural network. Journal of Shandong Jianzhu University. Vol. 33 (2018) No. 1, p. 25-31.

[18] L. Itti, C. Koch, E. Niebur,et al. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol.20(1998) No.11, p.1254-1259.

[19] J. Hu, L. Shen, G. Sun,et al. Squeeze-and-excitation networks. 2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, Utah, USA, 18-22 Jun. 2018, p.7132-7141.

[20] S. Woo, J. Park, J.-Y. Lee, et al. Cbam,et al. Convolutional block attention module. 2018 European Conference on Computer Vision. Munich, Germany, 8-14 Sep. 2018, p.3-19.

[21] B. Zhou, A. Khosla, A. Lapedriza, et al. Learning deep features for discriminative localization. 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 27-30 Jun. 2016, p.2921-2929.

[22] X. Wang, R. Girshick, A. Gupta, et al. Non-local neural networks. 2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, Utah, USA, 18-22 Jun. 2018, p.7794-7803.

[23] Garing S, Brand K, Raake A, et al. Extended features using machine learning techniques for photo liking predict. Tenth International Conference on Quality of Multimedia Experience. Cagliari, Italy, 2018, p.1-6.